Byanka's picture
commit from cp240
4b712a5
{
"best_metric": 1.386866569519043,
"best_model_checkpoint": "outputs_llama-2/checkpoint-240",
"epoch": 0.3702275356729657,
"eval_steps": 40,
"global_step": 240,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 2e-05,
"loss": 3.4868,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 4e-05,
"loss": 3.7961,
"step": 2
},
{
"epoch": 0.0,
"learning_rate": 6e-05,
"loss": 3.9117,
"step": 3
},
{
"epoch": 0.01,
"learning_rate": 8e-05,
"loss": 3.5057,
"step": 4
},
{
"epoch": 0.01,
"learning_rate": 0.0001,
"loss": 3.2378,
"step": 5
},
{
"epoch": 0.01,
"learning_rate": 0.00012,
"loss": 3.0761,
"step": 6
},
{
"epoch": 0.01,
"learning_rate": 0.00014,
"loss": 3.3794,
"step": 7
},
{
"epoch": 0.01,
"learning_rate": 0.00016,
"loss": 2.728,
"step": 8
},
{
"epoch": 0.01,
"learning_rate": 0.00018,
"loss": 2.5244,
"step": 9
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 2.47,
"step": 10
},
{
"epoch": 0.02,
"learning_rate": 0.00019968652037617558,
"loss": 2.5237,
"step": 11
},
{
"epoch": 0.02,
"learning_rate": 0.0001993730407523511,
"loss": 2.3919,
"step": 12
},
{
"epoch": 0.02,
"learning_rate": 0.00019905956112852667,
"loss": 1.9547,
"step": 13
},
{
"epoch": 0.02,
"learning_rate": 0.0001987460815047022,
"loss": 1.8513,
"step": 14
},
{
"epoch": 0.02,
"learning_rate": 0.00019843260188087775,
"loss": 1.6401,
"step": 15
},
{
"epoch": 0.02,
"learning_rate": 0.0001981191222570533,
"loss": 1.7872,
"step": 16
},
{
"epoch": 0.03,
"learning_rate": 0.00019780564263322884,
"loss": 1.8782,
"step": 17
},
{
"epoch": 0.03,
"learning_rate": 0.0001974921630094044,
"loss": 1.8139,
"step": 18
},
{
"epoch": 0.03,
"learning_rate": 0.00019717868338557995,
"loss": 1.5255,
"step": 19
},
{
"epoch": 0.03,
"learning_rate": 0.0001968652037617555,
"loss": 1.326,
"step": 20
},
{
"epoch": 0.03,
"learning_rate": 0.00019655172413793104,
"loss": 1.7972,
"step": 21
},
{
"epoch": 0.03,
"learning_rate": 0.0001962382445141066,
"loss": 1.4295,
"step": 22
},
{
"epoch": 0.04,
"learning_rate": 0.00019592476489028212,
"loss": 1.6369,
"step": 23
},
{
"epoch": 0.04,
"learning_rate": 0.0001956112852664577,
"loss": 1.7473,
"step": 24
},
{
"epoch": 0.04,
"learning_rate": 0.00019529780564263324,
"loss": 1.6524,
"step": 25
},
{
"epoch": 0.04,
"learning_rate": 0.00019498432601880878,
"loss": 1.5889,
"step": 26
},
{
"epoch": 0.04,
"learning_rate": 0.00019467084639498435,
"loss": 1.3206,
"step": 27
},
{
"epoch": 0.04,
"learning_rate": 0.00019435736677115987,
"loss": 1.9595,
"step": 28
},
{
"epoch": 0.04,
"learning_rate": 0.00019404388714733544,
"loss": 1.5356,
"step": 29
},
{
"epoch": 0.05,
"learning_rate": 0.00019373040752351098,
"loss": 1.932,
"step": 30
},
{
"epoch": 0.05,
"learning_rate": 0.00019341692789968652,
"loss": 1.3679,
"step": 31
},
{
"epoch": 0.05,
"learning_rate": 0.0001931034482758621,
"loss": 1.5176,
"step": 32
},
{
"epoch": 0.05,
"learning_rate": 0.0001927899686520376,
"loss": 1.774,
"step": 33
},
{
"epoch": 0.05,
"learning_rate": 0.00019247648902821318,
"loss": 1.4211,
"step": 34
},
{
"epoch": 0.05,
"learning_rate": 0.00019216300940438872,
"loss": 2.0095,
"step": 35
},
{
"epoch": 0.06,
"learning_rate": 0.00019184952978056427,
"loss": 1.1123,
"step": 36
},
{
"epoch": 0.06,
"learning_rate": 0.0001915360501567398,
"loss": 1.5061,
"step": 37
},
{
"epoch": 0.06,
"learning_rate": 0.00019122257053291538,
"loss": 1.8059,
"step": 38
},
{
"epoch": 0.06,
"learning_rate": 0.00019090909090909092,
"loss": 1.361,
"step": 39
},
{
"epoch": 0.06,
"learning_rate": 0.00019059561128526647,
"loss": 1.6624,
"step": 40
},
{
"epoch": 0.06,
"eval_loss": 1.4508017301559448,
"eval_runtime": 866.2645,
"eval_samples_per_second": 1.16,
"eval_steps_per_second": 1.16,
"step": 40
},
{
"epoch": 0.06,
"learning_rate": 0.000190282131661442,
"loss": 1.0086,
"step": 41
},
{
"epoch": 0.06,
"learning_rate": 0.00018996865203761755,
"loss": 1.8394,
"step": 42
},
{
"epoch": 0.07,
"learning_rate": 0.00018965517241379312,
"loss": 1.595,
"step": 43
},
{
"epoch": 0.07,
"learning_rate": 0.00018934169278996866,
"loss": 1.4083,
"step": 44
},
{
"epoch": 0.07,
"learning_rate": 0.0001890282131661442,
"loss": 1.6845,
"step": 45
},
{
"epoch": 0.07,
"learning_rate": 0.00018871473354231978,
"loss": 1.2298,
"step": 46
},
{
"epoch": 0.07,
"learning_rate": 0.0001884012539184953,
"loss": 1.0909,
"step": 47
},
{
"epoch": 0.07,
"learning_rate": 0.00018808777429467086,
"loss": 1.1942,
"step": 48
},
{
"epoch": 0.08,
"learning_rate": 0.0001877742946708464,
"loss": 1.7951,
"step": 49
},
{
"epoch": 0.08,
"learning_rate": 0.00018746081504702195,
"loss": 1.5837,
"step": 50
},
{
"epoch": 0.08,
"learning_rate": 0.00018714733542319752,
"loss": 1.1171,
"step": 51
},
{
"epoch": 0.08,
"learning_rate": 0.00018683385579937304,
"loss": 1.5556,
"step": 52
},
{
"epoch": 0.08,
"learning_rate": 0.0001865203761755486,
"loss": 1.6377,
"step": 53
},
{
"epoch": 0.08,
"learning_rate": 0.00018620689655172415,
"loss": 1.7227,
"step": 54
},
{
"epoch": 0.08,
"learning_rate": 0.0001858934169278997,
"loss": 1.6148,
"step": 55
},
{
"epoch": 0.09,
"learning_rate": 0.00018557993730407524,
"loss": 1.1987,
"step": 56
},
{
"epoch": 0.09,
"learning_rate": 0.0001852664576802508,
"loss": 0.8116,
"step": 57
},
{
"epoch": 0.09,
"learning_rate": 0.00018495297805642635,
"loss": 1.627,
"step": 58
},
{
"epoch": 0.09,
"learning_rate": 0.0001846394984326019,
"loss": 1.3519,
"step": 59
},
{
"epoch": 0.09,
"learning_rate": 0.00018432601880877744,
"loss": 1.1224,
"step": 60
},
{
"epoch": 0.09,
"learning_rate": 0.00018401253918495298,
"loss": 1.4279,
"step": 61
},
{
"epoch": 0.1,
"learning_rate": 0.00018369905956112855,
"loss": 1.3011,
"step": 62
},
{
"epoch": 0.1,
"learning_rate": 0.00018338557993730406,
"loss": 1.654,
"step": 63
},
{
"epoch": 0.1,
"learning_rate": 0.00018307210031347963,
"loss": 0.8621,
"step": 64
},
{
"epoch": 0.1,
"learning_rate": 0.00018275862068965518,
"loss": 1.3778,
"step": 65
},
{
"epoch": 0.1,
"learning_rate": 0.00018244514106583072,
"loss": 1.7181,
"step": 66
},
{
"epoch": 0.1,
"learning_rate": 0.0001821316614420063,
"loss": 1.603,
"step": 67
},
{
"epoch": 0.1,
"learning_rate": 0.00018181818181818183,
"loss": 1.3475,
"step": 68
},
{
"epoch": 0.11,
"learning_rate": 0.00018150470219435738,
"loss": 1.7242,
"step": 69
},
{
"epoch": 0.11,
"learning_rate": 0.00018119122257053292,
"loss": 1.58,
"step": 70
},
{
"epoch": 0.11,
"learning_rate": 0.00018087774294670846,
"loss": 1.4371,
"step": 71
},
{
"epoch": 0.11,
"learning_rate": 0.00018056426332288403,
"loss": 1.3795,
"step": 72
},
{
"epoch": 0.11,
"learning_rate": 0.00018025078369905958,
"loss": 1.1421,
"step": 73
},
{
"epoch": 0.11,
"learning_rate": 0.00017993730407523512,
"loss": 1.1617,
"step": 74
},
{
"epoch": 0.12,
"learning_rate": 0.00017962382445141066,
"loss": 1.4031,
"step": 75
},
{
"epoch": 0.12,
"learning_rate": 0.0001793103448275862,
"loss": 2.0192,
"step": 76
},
{
"epoch": 0.12,
"learning_rate": 0.00017899686520376175,
"loss": 1.4762,
"step": 77
},
{
"epoch": 0.12,
"learning_rate": 0.00017868338557993732,
"loss": 1.4992,
"step": 78
},
{
"epoch": 0.12,
"learning_rate": 0.00017836990595611286,
"loss": 1.5983,
"step": 79
},
{
"epoch": 0.12,
"learning_rate": 0.0001780564263322884,
"loss": 1.3888,
"step": 80
},
{
"epoch": 0.12,
"eval_loss": 1.416973352432251,
"eval_runtime": 866.3924,
"eval_samples_per_second": 1.16,
"eval_steps_per_second": 1.16,
"step": 80
},
{
"epoch": 0.12,
"learning_rate": 0.00017774294670846398,
"loss": 1.0799,
"step": 81
},
{
"epoch": 0.13,
"learning_rate": 0.0001774294670846395,
"loss": 1.3961,
"step": 82
},
{
"epoch": 0.13,
"learning_rate": 0.00017711598746081506,
"loss": 1.5792,
"step": 83
},
{
"epoch": 0.13,
"learning_rate": 0.0001768025078369906,
"loss": 1.6384,
"step": 84
},
{
"epoch": 0.13,
"learning_rate": 0.00017648902821316615,
"loss": 1.3299,
"step": 85
},
{
"epoch": 0.13,
"learning_rate": 0.00017617554858934172,
"loss": 1.7483,
"step": 86
},
{
"epoch": 0.13,
"learning_rate": 0.00017586206896551723,
"loss": 1.7161,
"step": 87
},
{
"epoch": 0.14,
"learning_rate": 0.0001755485893416928,
"loss": 1.3523,
"step": 88
},
{
"epoch": 0.14,
"learning_rate": 0.00017523510971786835,
"loss": 1.5451,
"step": 89
},
{
"epoch": 0.14,
"learning_rate": 0.0001749216300940439,
"loss": 1.4589,
"step": 90
},
{
"epoch": 0.14,
"learning_rate": 0.00017460815047021943,
"loss": 1.4352,
"step": 91
},
{
"epoch": 0.14,
"learning_rate": 0.000174294670846395,
"loss": 1.5711,
"step": 92
},
{
"epoch": 0.14,
"learning_rate": 0.00017398119122257055,
"loss": 1.3834,
"step": 93
},
{
"epoch": 0.15,
"learning_rate": 0.0001736677115987461,
"loss": 1.3734,
"step": 94
},
{
"epoch": 0.15,
"learning_rate": 0.00017335423197492163,
"loss": 1.5402,
"step": 95
},
{
"epoch": 0.15,
"learning_rate": 0.00017304075235109718,
"loss": 1.5848,
"step": 96
},
{
"epoch": 0.15,
"learning_rate": 0.00017272727272727275,
"loss": 1.3129,
"step": 97
},
{
"epoch": 0.15,
"learning_rate": 0.00017241379310344826,
"loss": 1.3945,
"step": 98
},
{
"epoch": 0.15,
"learning_rate": 0.00017210031347962383,
"loss": 1.79,
"step": 99
},
{
"epoch": 0.15,
"learning_rate": 0.0001717868338557994,
"loss": 1.0874,
"step": 100
},
{
"epoch": 0.16,
"learning_rate": 0.00017147335423197492,
"loss": 1.617,
"step": 101
},
{
"epoch": 0.16,
"learning_rate": 0.0001711598746081505,
"loss": 1.259,
"step": 102
},
{
"epoch": 0.16,
"learning_rate": 0.00017084639498432603,
"loss": 1.577,
"step": 103
},
{
"epoch": 0.16,
"learning_rate": 0.00017053291536050158,
"loss": 1.3163,
"step": 104
},
{
"epoch": 0.16,
"learning_rate": 0.00017021943573667712,
"loss": 1.3077,
"step": 105
},
{
"epoch": 0.16,
"learning_rate": 0.00016990595611285266,
"loss": 1.2611,
"step": 106
},
{
"epoch": 0.17,
"learning_rate": 0.00016959247648902823,
"loss": 1.8003,
"step": 107
},
{
"epoch": 0.17,
"learning_rate": 0.00016927899686520377,
"loss": 1.3783,
"step": 108
},
{
"epoch": 0.17,
"learning_rate": 0.00016896551724137932,
"loss": 1.3896,
"step": 109
},
{
"epoch": 0.17,
"learning_rate": 0.00016865203761755486,
"loss": 1.4663,
"step": 110
},
{
"epoch": 0.17,
"learning_rate": 0.0001683385579937304,
"loss": 0.7607,
"step": 111
},
{
"epoch": 0.17,
"learning_rate": 0.00016802507836990597,
"loss": 0.9899,
"step": 112
},
{
"epoch": 0.17,
"learning_rate": 0.00016771159874608152,
"loss": 1.8002,
"step": 113
},
{
"epoch": 0.18,
"learning_rate": 0.00016739811912225706,
"loss": 1.5776,
"step": 114
},
{
"epoch": 0.18,
"learning_rate": 0.0001670846394984326,
"loss": 1.551,
"step": 115
},
{
"epoch": 0.18,
"learning_rate": 0.00016677115987460817,
"loss": 1.4058,
"step": 116
},
{
"epoch": 0.18,
"learning_rate": 0.0001664576802507837,
"loss": 1.0475,
"step": 117
},
{
"epoch": 0.18,
"learning_rate": 0.00016614420062695926,
"loss": 1.7153,
"step": 118
},
{
"epoch": 0.18,
"learning_rate": 0.0001658307210031348,
"loss": 1.6289,
"step": 119
},
{
"epoch": 0.19,
"learning_rate": 0.00016551724137931035,
"loss": 1.2282,
"step": 120
},
{
"epoch": 0.19,
"eval_loss": 1.4044392108917236,
"eval_runtime": 866.8231,
"eval_samples_per_second": 1.159,
"eval_steps_per_second": 1.159,
"step": 120
},
{
"epoch": 0.19,
"learning_rate": 0.00016520376175548592,
"loss": 1.6396,
"step": 121
},
{
"epoch": 0.19,
"learning_rate": 0.00016489028213166143,
"loss": 1.7545,
"step": 122
},
{
"epoch": 0.19,
"learning_rate": 0.000164576802507837,
"loss": 1.3772,
"step": 123
},
{
"epoch": 0.19,
"learning_rate": 0.00016426332288401255,
"loss": 1.2632,
"step": 124
},
{
"epoch": 0.19,
"learning_rate": 0.0001639498432601881,
"loss": 1.0961,
"step": 125
},
{
"epoch": 0.19,
"learning_rate": 0.00016363636363636366,
"loss": 1.228,
"step": 126
},
{
"epoch": 0.2,
"learning_rate": 0.0001633228840125392,
"loss": 1.8272,
"step": 127
},
{
"epoch": 0.2,
"learning_rate": 0.00016300940438871475,
"loss": 1.2743,
"step": 128
},
{
"epoch": 0.2,
"learning_rate": 0.0001626959247648903,
"loss": 1.3611,
"step": 129
},
{
"epoch": 0.2,
"learning_rate": 0.00016238244514106583,
"loss": 1.2495,
"step": 130
},
{
"epoch": 0.2,
"learning_rate": 0.00016206896551724137,
"loss": 1.2027,
"step": 131
},
{
"epoch": 0.2,
"learning_rate": 0.00016175548589341694,
"loss": 1.0558,
"step": 132
},
{
"epoch": 0.21,
"learning_rate": 0.0001614420062695925,
"loss": 1.1034,
"step": 133
},
{
"epoch": 0.21,
"learning_rate": 0.00016112852664576803,
"loss": 1.7864,
"step": 134
},
{
"epoch": 0.21,
"learning_rate": 0.0001608150470219436,
"loss": 1.3586,
"step": 135
},
{
"epoch": 0.21,
"learning_rate": 0.00016050156739811912,
"loss": 1.639,
"step": 136
},
{
"epoch": 0.21,
"learning_rate": 0.0001601880877742947,
"loss": 1.4719,
"step": 137
},
{
"epoch": 0.21,
"learning_rate": 0.00015987460815047023,
"loss": 1.7374,
"step": 138
},
{
"epoch": 0.21,
"learning_rate": 0.00015956112852664577,
"loss": 1.5463,
"step": 139
},
{
"epoch": 0.22,
"learning_rate": 0.00015924764890282134,
"loss": 1.2065,
"step": 140
},
{
"epoch": 0.22,
"learning_rate": 0.00015893416927899686,
"loss": 1.1328,
"step": 141
},
{
"epoch": 0.22,
"learning_rate": 0.00015862068965517243,
"loss": 1.2139,
"step": 142
},
{
"epoch": 0.22,
"learning_rate": 0.00015830721003134797,
"loss": 1.5045,
"step": 143
},
{
"epoch": 0.22,
"learning_rate": 0.00015799373040752352,
"loss": 1.676,
"step": 144
},
{
"epoch": 0.22,
"learning_rate": 0.00015768025078369906,
"loss": 1.3679,
"step": 145
},
{
"epoch": 0.23,
"learning_rate": 0.0001573667711598746,
"loss": 1.3023,
"step": 146
},
{
"epoch": 0.23,
"learning_rate": 0.00015705329153605017,
"loss": 0.6768,
"step": 147
},
{
"epoch": 0.23,
"learning_rate": 0.00015673981191222572,
"loss": 1.2916,
"step": 148
},
{
"epoch": 0.23,
"learning_rate": 0.00015642633228840126,
"loss": 1.343,
"step": 149
},
{
"epoch": 0.23,
"learning_rate": 0.0001561128526645768,
"loss": 1.1307,
"step": 150
},
{
"epoch": 0.23,
"learning_rate": 0.00015579937304075237,
"loss": 1.277,
"step": 151
},
{
"epoch": 0.23,
"learning_rate": 0.0001554858934169279,
"loss": 0.948,
"step": 152
},
{
"epoch": 0.24,
"learning_rate": 0.00015517241379310346,
"loss": 1.4819,
"step": 153
},
{
"epoch": 0.24,
"learning_rate": 0.000154858934169279,
"loss": 1.7333,
"step": 154
},
{
"epoch": 0.24,
"learning_rate": 0.00015454545454545454,
"loss": 1.302,
"step": 155
},
{
"epoch": 0.24,
"learning_rate": 0.00015423197492163011,
"loss": 1.3045,
"step": 156
},
{
"epoch": 0.24,
"learning_rate": 0.00015391849529780563,
"loss": 1.2773,
"step": 157
},
{
"epoch": 0.24,
"learning_rate": 0.0001536050156739812,
"loss": 0.4272,
"step": 158
},
{
"epoch": 0.25,
"learning_rate": 0.00015329153605015674,
"loss": 1.3533,
"step": 159
},
{
"epoch": 0.25,
"learning_rate": 0.0001529780564263323,
"loss": 1.2623,
"step": 160
},
{
"epoch": 0.25,
"eval_loss": 1.399330735206604,
"eval_runtime": 866.2143,
"eval_samples_per_second": 1.16,
"eval_steps_per_second": 1.16,
"step": 160
},
{
"epoch": 0.25,
"learning_rate": 0.00015266457680250786,
"loss": 1.2428,
"step": 161
},
{
"epoch": 0.25,
"learning_rate": 0.0001523510971786834,
"loss": 1.1193,
"step": 162
},
{
"epoch": 0.25,
"learning_rate": 0.00015203761755485894,
"loss": 1.7799,
"step": 163
},
{
"epoch": 0.25,
"learning_rate": 0.00015172413793103449,
"loss": 1.8581,
"step": 164
},
{
"epoch": 0.25,
"learning_rate": 0.00015141065830721003,
"loss": 1.3594,
"step": 165
},
{
"epoch": 0.26,
"learning_rate": 0.00015109717868338557,
"loss": 1.1355,
"step": 166
},
{
"epoch": 0.26,
"learning_rate": 0.00015078369905956114,
"loss": 1.2911,
"step": 167
},
{
"epoch": 0.26,
"learning_rate": 0.00015047021943573669,
"loss": 1.1215,
"step": 168
},
{
"epoch": 0.26,
"learning_rate": 0.00015015673981191223,
"loss": 1.3987,
"step": 169
},
{
"epoch": 0.26,
"learning_rate": 0.0001498432601880878,
"loss": 1.4536,
"step": 170
},
{
"epoch": 0.26,
"learning_rate": 0.00014952978056426332,
"loss": 1.3232,
"step": 171
},
{
"epoch": 0.27,
"learning_rate": 0.00014921630094043889,
"loss": 1.2199,
"step": 172
},
{
"epoch": 0.27,
"learning_rate": 0.00014890282131661443,
"loss": 1.5375,
"step": 173
},
{
"epoch": 0.27,
"learning_rate": 0.00014858934169278997,
"loss": 1.6982,
"step": 174
},
{
"epoch": 0.27,
"learning_rate": 0.00014827586206896554,
"loss": 1.6182,
"step": 175
},
{
"epoch": 0.27,
"learning_rate": 0.00014796238244514106,
"loss": 1.3373,
"step": 176
},
{
"epoch": 0.27,
"learning_rate": 0.00014764890282131663,
"loss": 1.4321,
"step": 177
},
{
"epoch": 0.27,
"learning_rate": 0.00014733542319749217,
"loss": 1.2147,
"step": 178
},
{
"epoch": 0.28,
"learning_rate": 0.00014702194357366771,
"loss": 1.6977,
"step": 179
},
{
"epoch": 0.28,
"learning_rate": 0.00014670846394984328,
"loss": 1.562,
"step": 180
},
{
"epoch": 0.28,
"learning_rate": 0.0001463949843260188,
"loss": 1.3612,
"step": 181
},
{
"epoch": 0.28,
"learning_rate": 0.00014608150470219437,
"loss": 1.4421,
"step": 182
},
{
"epoch": 0.28,
"learning_rate": 0.0001457680250783699,
"loss": 1.201,
"step": 183
},
{
"epoch": 0.28,
"learning_rate": 0.00014545454545454546,
"loss": 1.5015,
"step": 184
},
{
"epoch": 0.29,
"learning_rate": 0.000145141065830721,
"loss": 1.8102,
"step": 185
},
{
"epoch": 0.29,
"learning_rate": 0.00014482758620689657,
"loss": 1.1975,
"step": 186
},
{
"epoch": 0.29,
"learning_rate": 0.0001445141065830721,
"loss": 1.2328,
"step": 187
},
{
"epoch": 0.29,
"learning_rate": 0.00014420062695924766,
"loss": 1.8503,
"step": 188
},
{
"epoch": 0.29,
"learning_rate": 0.0001438871473354232,
"loss": 0.9917,
"step": 189
},
{
"epoch": 0.29,
"learning_rate": 0.00014357366771159874,
"loss": 1.1511,
"step": 190
},
{
"epoch": 0.29,
"learning_rate": 0.0001432601880877743,
"loss": 1.4227,
"step": 191
},
{
"epoch": 0.3,
"learning_rate": 0.00014294670846394983,
"loss": 1.5738,
"step": 192
},
{
"epoch": 0.3,
"learning_rate": 0.0001426332288401254,
"loss": 1.6898,
"step": 193
},
{
"epoch": 0.3,
"learning_rate": 0.00014231974921630097,
"loss": 1.2109,
"step": 194
},
{
"epoch": 0.3,
"learning_rate": 0.00014200626959247648,
"loss": 1.5157,
"step": 195
},
{
"epoch": 0.3,
"learning_rate": 0.00014169278996865206,
"loss": 1.4976,
"step": 196
},
{
"epoch": 0.3,
"learning_rate": 0.0001413793103448276,
"loss": 1.9071,
"step": 197
},
{
"epoch": 0.31,
"learning_rate": 0.00014106583072100314,
"loss": 1.436,
"step": 198
},
{
"epoch": 0.31,
"learning_rate": 0.00014075235109717868,
"loss": 1.4321,
"step": 199
},
{
"epoch": 0.31,
"learning_rate": 0.00014043887147335423,
"loss": 1.5108,
"step": 200
},
{
"epoch": 0.31,
"eval_loss": 1.3920130729675293,
"eval_runtime": 866.972,
"eval_samples_per_second": 1.159,
"eval_steps_per_second": 1.159,
"step": 200
},
{
"epoch": 0.31,
"learning_rate": 0.0001401253918495298,
"loss": 1.2756,
"step": 201
},
{
"epoch": 0.31,
"learning_rate": 0.00013981191222570534,
"loss": 1.4882,
"step": 202
},
{
"epoch": 0.31,
"learning_rate": 0.00013949843260188088,
"loss": 1.484,
"step": 203
},
{
"epoch": 0.31,
"learning_rate": 0.00013918495297805643,
"loss": 1.6371,
"step": 204
},
{
"epoch": 0.32,
"learning_rate": 0.000138871473354232,
"loss": 0.6986,
"step": 205
},
{
"epoch": 0.32,
"learning_rate": 0.0001385579937304075,
"loss": 1.469,
"step": 206
},
{
"epoch": 0.32,
"learning_rate": 0.00013824451410658308,
"loss": 1.4841,
"step": 207
},
{
"epoch": 0.32,
"learning_rate": 0.00013793103448275863,
"loss": 1.06,
"step": 208
},
{
"epoch": 0.32,
"learning_rate": 0.00013761755485893417,
"loss": 1.7007,
"step": 209
},
{
"epoch": 0.32,
"learning_rate": 0.00013730407523510974,
"loss": 1.5835,
"step": 210
},
{
"epoch": 0.33,
"learning_rate": 0.00013699059561128526,
"loss": 1.7115,
"step": 211
},
{
"epoch": 0.33,
"learning_rate": 0.00013667711598746083,
"loss": 1.1916,
"step": 212
},
{
"epoch": 0.33,
"learning_rate": 0.00013636363636363637,
"loss": 1.4264,
"step": 213
},
{
"epoch": 0.33,
"learning_rate": 0.0001360501567398119,
"loss": 1.6938,
"step": 214
},
{
"epoch": 0.33,
"learning_rate": 0.00013573667711598748,
"loss": 1.1683,
"step": 215
},
{
"epoch": 0.33,
"learning_rate": 0.00013542319749216303,
"loss": 1.6196,
"step": 216
},
{
"epoch": 0.33,
"learning_rate": 0.00013510971786833857,
"loss": 1.1304,
"step": 217
},
{
"epoch": 0.34,
"learning_rate": 0.0001347962382445141,
"loss": 0.9536,
"step": 218
},
{
"epoch": 0.34,
"learning_rate": 0.00013448275862068965,
"loss": 1.4981,
"step": 219
},
{
"epoch": 0.34,
"learning_rate": 0.0001341692789968652,
"loss": 1.5185,
"step": 220
},
{
"epoch": 0.34,
"learning_rate": 0.00013385579937304077,
"loss": 1.2294,
"step": 221
},
{
"epoch": 0.34,
"learning_rate": 0.0001335423197492163,
"loss": 1.7871,
"step": 222
},
{
"epoch": 0.34,
"learning_rate": 0.00013322884012539185,
"loss": 1.2107,
"step": 223
},
{
"epoch": 0.35,
"learning_rate": 0.0001329153605015674,
"loss": 1.4636,
"step": 224
},
{
"epoch": 0.35,
"learning_rate": 0.00013260188087774294,
"loss": 1.1326,
"step": 225
},
{
"epoch": 0.35,
"learning_rate": 0.0001322884012539185,
"loss": 1.4011,
"step": 226
},
{
"epoch": 0.35,
"learning_rate": 0.00013197492163009403,
"loss": 1.4236,
"step": 227
},
{
"epoch": 0.35,
"learning_rate": 0.0001316614420062696,
"loss": 1.35,
"step": 228
},
{
"epoch": 0.35,
"learning_rate": 0.00013134796238244517,
"loss": 1.3837,
"step": 229
},
{
"epoch": 0.35,
"learning_rate": 0.00013103448275862068,
"loss": 1.1546,
"step": 230
},
{
"epoch": 0.36,
"learning_rate": 0.00013072100313479625,
"loss": 1.4603,
"step": 231
},
{
"epoch": 0.36,
"learning_rate": 0.0001304075235109718,
"loss": 1.4694,
"step": 232
},
{
"epoch": 0.36,
"learning_rate": 0.00013009404388714734,
"loss": 0.9677,
"step": 233
},
{
"epoch": 0.36,
"learning_rate": 0.0001297805642633229,
"loss": 1.4057,
"step": 234
},
{
"epoch": 0.36,
"learning_rate": 0.00012946708463949843,
"loss": 1.5458,
"step": 235
},
{
"epoch": 0.36,
"learning_rate": 0.000129153605015674,
"loss": 1.4101,
"step": 236
},
{
"epoch": 0.37,
"learning_rate": 0.00012884012539184954,
"loss": 1.4087,
"step": 237
},
{
"epoch": 0.37,
"learning_rate": 0.00012852664576802508,
"loss": 1.2849,
"step": 238
},
{
"epoch": 0.37,
"learning_rate": 0.00012821316614420062,
"loss": 1.73,
"step": 239
},
{
"epoch": 0.37,
"learning_rate": 0.0001278996865203762,
"loss": 1.4046,
"step": 240
},
{
"epoch": 0.37,
"eval_loss": 1.386866569519043,
"eval_runtime": 866.0039,
"eval_samples_per_second": 1.161,
"eval_steps_per_second": 1.161,
"step": 240
}
],
"logging_steps": 1,
"max_steps": 648,
"num_train_epochs": 1,
"save_steps": 40,
"total_flos": 1.1654508112084992e+16,
"trial_name": null,
"trial_params": null
}